xiaji
8600c0f576
- 实现智能区域检测算法（灰度阈值 + 连续行判定） - 支持Umi-OCR和自定义HTTP OCR服务 - 添加热键触发和鼠标框选区域功能 - 实现自动滚动和智能停止逻辑 - 添加完整的README文档
147 lines
4.1 KiB
Python
147 lines
4.1 KiB
Python
"""
|
||
OCR服务示例实现
|
||
这是一个简单的OCR HTTP服务示例，使用 PaddleOCR 或 Tesseract 作为后端
|
||
你可以根据实际需求修改此文件或使用其他OCR服务
|
||
|
||
启动方式: python ocr_server_example.py
|
||
服务地址: http://localhost:8000
|
||
"""
|
||
|
||
import base64
|
||
import io
|
||
from typing import List
|
||
|
||
try:
|
||
from flask import Flask, request, jsonify
|
||
except ImportError:
|
||
print("请先安装Flask: pip install flask")
|
||
raise
|
||
|
||
try:
|
||
from PIL import Image
|
||
except ImportError:
|
||
print("请先安装Pillow: pip install pillow")
|
||
raise
|
||
|
||
app = Flask(__name__)
|
||
|
||
# 尝试导入OCR引擎，按优先级：PaddleOCR > Tesseract > 模拟
|
||
ocr_engine = None
|
||
ocr_type = None
|
||
|
||
try:
|
||
from paddleocr import PaddleOCR
|
||
ocr_engine = PaddleOCR(
|
||
use_angle_cls=True,
|
||
lang='ch',
|
||
show_log=False
|
||
)
|
||
ocr_type = "paddle"
|
||
print("使用 PaddleOCR 引擎")
|
||
except ImportError:
|
||
try:
|
||
import pytesseract
|
||
ocr_engine = pytesseract
|
||
ocr_type = "tesseract"
|
||
print("使用 Tesseract OCR 引擎")
|
||
except ImportError:
|
||
ocr_type = "mock"
|
||
print("警告: 未找到OCR引擎，使用模拟模式")
|
||
print("建议安装 PaddleOCR: pip install paddleocr")
|
||
print("或安装 Tesseract + pytesseract: pip install pytesseract")
|
||
|
||
|
||
def recognize_with_paddle(image: Image.Image) -> List[str]:
|
||
"""使用PaddleOCR识别"""
|
||
import numpy as np
|
||
img_array = np.array(image)
|
||
result = ocr_engine.ocr(img_array, cls=True)
|
||
|
||
texts = []
|
||
if result and result[0]:
|
||
for line in result[0]:
|
||
if line:
|
||
text = line[1][0] # 提取文字内容
|
||
confidence = line[1][1] # 置信度
|
||
if confidence > 0.5: # 过滤低置信度结果
|
||
texts.append(text)
|
||
return texts
|
||
|
||
|
||
def recognize_with_tesseract(image: Image.Image) -> List[str]:
|
||
"""使用Tesseract识别"""
|
||
text = ocr_engine.image_to_string(image, lang='chi_sim+eng')
|
||
# 按行分割
|
||
lines = [line.strip() for line in text.split('\n') if line.strip()]
|
||
return lines
|
||
|
||
|
||
def recognize_mock(image: Image.Image) -> List[str]:
|
||
"""模拟OCR（用于测试）"""
|
||
return ["[模拟OCR] 请安装实际的OCR引擎"]
|
||
|
||
|
||
def recognize_image(image: Image.Image) -> List[str]:
|
||
"""根据配置的引擎进行识别"""
|
||
if ocr_type == "paddle":
|
||
return recognize_with_paddle(image)
|
||
elif ocr_type == "tesseract":
|
||
return recognize_with_tesseract(image)
|
||
else:
|
||
return recognize_mock(image)
|
||
|
||
|
||
@app.route('/ocr', methods=['POST'])
|
||
def ocr_endpoint():
|
||
"""
|
||
OCR API端点
|
||
接收JSON: {"image": "base64编码的图片"}
|
||
返回JSON: {"texts": ["识别到的文字1", "识别到的文字2", ...]}
|
||
"""
|
||
try:
|
||
data = request.get_json()
|
||
if not data or 'image' not in data:
|
||
return jsonify({"error": "缺少image字段"}), 400
|
||
|
||
# 解码base64图片
|
||
img_base64 = data['image']
|
||
img_data = base64.b64decode(img_base64)
|
||
image = Image.open(io.BytesIO(img_data))
|
||
|
||
# 转换为RGB（如果是RGBA或其他模式）
|
||
if image.mode != 'RGB':
|
||
image = image.convert('RGB')
|
||
|
||
# 执行OCR
|
||
texts = recognize_image(image)
|
||
|
||
return jsonify({
|
||
"texts": texts,
|
||
"count": len(texts),
|
||
"engine": ocr_type
|
||
})
|
||
|
||
except Exception as e:
|
||
return jsonify({"error": str(e)}), 500
|
||
|
||
|
||
@app.route('/health', methods=['GET'])
|
||
def health_check():
|
||
"""健康检查端点"""
|
||
return jsonify({
|
||
"status": "ok",
|
||
"engine": ocr_type
|
||
})
|
||
|
||
|
||
if __name__ == '__main__':
|
||
print("=" * 60)
|
||
print("OCR HTTP 服务")
|
||
print("=" * 60)
|
||
print(f"OCR引擎: {ocr_type}")
|
||
print("API地址: http://localhost:8000/ocr")
|
||
print("健康检查: http://localhost:8000/health")
|
||
print("=" * 60)
|
||
print("\n启动服务中...")
|
||
app.run(host='0.0.0.0', port=8000, debug=False)
|